© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31997
    Prev
    Next
    INDEX
    Explanations

    dairy farming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĽĴåŃIJ
    -0.10
    æĴŀåĩ»
    -0.09
    èıľé¸Ł
    -0.09
    oons
    -0.09
    ä¿¡ç®±
    -0.09
    诣
    -0.09
    çĻ»å±±
    -0.09
    æĸ¹å½¢
    -0.09
    åį°
    -0.08
    ÙĨÙħ
    -0.08
    POSITIVE LOGITS
    饲
    0.09
    æĸ¯åŁº
    0.09
    vc
    0.08
    çĭ¸
    0.08
     sil
    0.08
    建çŃijä¸ļ
    0.08
     husband
    0.08
    è§ĦåĪĴ设计
    0.08
    ä¼ĺåĮĸ
    0.08
    çīĽå¥¶
    0.08
    Activations Density 0.266%

    No Known Activations